深度学习下主流染色体分类算法的性能评估  

Performance evaluation of mainstream chromosome recognition algorithms under deep learning

作　　者：易序晟 尹爱华[4] 黄杰晟 彭璟 陈汉彪[4] 郭莉[4] 林成创[1,2,3] 李双印 赵淦森 Yi Xusheng;Yin Aihua;Huang Jiesheng;Peng Jing;Chen Hanbiao;Guo Li;Lin Chengchuang;Li Shuangyin;Zhao Gansen(School of Computer Science and Technology,South China Normal University,Guangzhou 510631,China;Key Laboratory on Cloud Security and Assessment Technology of Guangzhou,Guangzhou 510631,China;VeChain Blockchain Technology and Application Joint Laboratory,South China Normal University,Guangzhou 510631,China;Guangdong Maternity and Child Health Hospital,Guangzhou 511400,China)

机构地区：[1]华南师范大学计算机学院,广州510631 [2]广州市云计算安全与测评技术重点实验室,广州510631 [3]华南师范大学唯链区块链技术与应用联合实验室,广州510631 [4]广东省妇幼保健院,广州511400

出　　处：《中国图象图形学报》2023年第2期570-588,共19页Journal of Image and Graphics

基　　金：国家重点研发计划资助(2018YFB1404402);国家社会科学基金重大项目(19ZDA041);中国高校产学研创新基金——新一代信息技术创新项目——基于区块链的专利申请前评估的模型定制技术(2020ITA09006)。

摘　　要：目的染色体分类是医学影像处理的具体任务之一,最终结果可为医生提供重要的临床诊断信息,在产前诊断中起着重要作用。深度学习由于强大的特征表达能力在医学影像领域得到了广泛应用,但是基于深度学习的大部分染色体分类算法都是在轻量化私有数据库上得到的不同水准的分类结果,难以客观评估不同算法间的优劣,导致缺乏对算法的临床筛选标准,因此迫切需要在大规模数据库上对不同算法开展基于同样数据级的性能评估,以获取具有客观可对比性的性能数据,这对于科研成果的转化具有重要意义。方法本文基于广东省妇幼保健院提供的染色体数据,构建了包含126453条染色体的临床数据库,精选6个主流染色体分类模型在该数据库上展开对比实验与性能评估。结果在本文构建的大规模染色体临床数据库上,实验和分析发现,参评模型分类准确率均达到92%以上,其中MixNet模型提升后分类效果最好,为98.92%。即使分类性能落后的模型在本数据集上训练也得到明显改善,准确率从86.7%提升至92.09%,相比早期报告的性能提升了5.39%。结论开展实证研究实验发现,数据库规模大小是影响染色体分类算法能否取得理想分类效果的重要因素之一。对于染色体分类任务而言,残差神经网络是比较合适的网络结构,但结果方面缺乏可解释性等原因,导致与高精度临床应用要求还存在差距。基于深度学习技术的染色体分类研究还需要进一步深入开展。Objective Deep learning technique-based medicinal image processing is essential for clinical information in related to disease diagnosis,treatment,and surgical planning.Chromosome-relevant segmentation can be as one of the specific tasks for medical-based image processing.It is beneficial to prenatal diagnosis via clinical diagnosis information gathering and analysis.In recent years,an end-to-end training features-based deep learning technique has been developing intensively.Chromosome-relevant segmentation has been facilitating as well.Chromosomes can be one of the key carriers of genetic information.Chromosomes-based genetic information analysis is often employed for human genetic diseases.Chromosome images-related kaiyotyping analysis is a commonly-used method for diagnosing birth defects and it can be as the"gold standard"for the clinical diagnosis of genetic diseases.Chromosome segmentation is challenged for the manipulation problem in the context of chromosome karyotype analysis.It has a strong reference value for prenatal diagnosis results.However,most of chromosome-related segmentation algorithms have restricted by its heterogeneity,resulting in a lack of a screening standard for algorithms in clinical applications.To carry out more comparative experiments on the large-scale chromosome-constructed database,we develop a multiple of chromosome-essential segmentation models.Method Our database is constructed and segmented in terms of the chromosome karyotype(funded by Guangdong Maternity and Child Health Hospital).first,it consists of large-scale chromosome clinical data in relevant to 126453 chromosome samples.Then,the publicly-available multi-chromosome-essential recognition models are selected.Finally,experiments and performance evaluation of our model is carried out in the clinical chromosome database.Result Random sampling-stratified experiment is used to divide the clinical chromosome data set into training data set(80%),validation data set(10%),and test data set(10%)totally.The models-selected are all

关 键 词：医学影像处理 深度学习 染色体分类 残差神经网络 分类评估 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]